Modelling and Optimisation of Biodiesel Production from Margarine Waste Oil Using a Three-Dimensional Machine Learning Approach

The development of low-carbon and environmentally friendly energy sources has led to much research on the production and optimisation of biodiesel. This work presents the use of three-dimensional machine learning approaches, namely response surface methodology (RSM), an artificial neural network (ANN), and an adaptive neuro-fuzzy inference system (ANFIS) to optimise and model biodiesel production from margarine waste oil. The effect of process parameters, e.g., the methanol to oil ratio (3-15 mole ), catalyst ratio ( 0.3-1.5wt. %), reaction time (30-90 minutes), and reaction temperature ( 30-70 ^oC), was studied. RSM was used for process optimisation. Model construction of the ANN model used 70% of the data for training, 15% for testing, and 15% for validation. The network was trained using feed-forward propagation and the Levenberg–Marquardt algorithm. The ANFIS was generated using a grid partition and trained using a hybrid method. The effectiveness of the machine learning was assessed through error metrics such as regression (R²), root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), average relative error (ARE), and mean percent standard deviation (MPSD). The optimum yield was obtained with a 9 mole ratio, 0.9 wt. % catalyst ratio, 60 minute reaction time, and 50 ^oC reaction temperature, with 89.09%. According to the results, the developed three-dimensional machine learning approach—the RSM, ANN, and ANFIS models—is a potential method for optimising and modelling the production of biodiesel from waste margarine oil. The study results may be used to create sustainable, efficient, and economical solutions for recycling waste margarine oil.